Triple
T8261467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hurricane Irma |
E193203
|
entity |
| Predicate | trackOrigin |
P3654
|
FINISHED |
| Object | off the west coast of Africa |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: off the west coast of Africa | Statement: [Hurricane Irma, trackOrigin, off the west coast of Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trackOrigin Context triple: [Hurricane Irma, trackOrigin, off the west coast of Africa]
-
A.
routeOrigin
Indicates the starting point or source location from which a route begins.
-
B.
originatesAs
Indicates that one entity begins, arises, or comes into existence in the form, state, or role specified by another entity.
-
C.
collectionOrigin
Indicates that one entity is the source, provenance, or originating context from which a collection of items or data has been derived or assembled.
-
D.
hasOriginIn
chosen
Indicates that something begins, arises, or is derived from a specified source, place, or cause.
-
E.
trackOn
Indicates that one entity is physically positioned or moving along the surface or path of another, like a vehicle on a track or rails.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca82e081d48190986beaa51f498ab9 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7936b72c8190b998da033df611d1 |
completed | March 31, 2026, 7:35 a.m. |
| PD | Predicate disambiguation | batch_69cb36b8707881909aca349230495a5a |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:49 p.m.